WNPWR: Web navigation prediction framework for webpage recommendation

Abstract

Huge amount of user request data is generated in web-log. Predicting users' future requests based on previously visited pages is important for web page recommendation, reduction of latency, on-line advertising etc. These applications compromise with prediction accuracy and modelling complexity. we propose a Web Navigation Prediction Framework for webpage Recommendation(WNPWR) which creates and generates a classifier based on sessions as training examples. As sessions are used as training examples, they are created by calculating average time on visiting web pages rather than traditional method which uses 30 minutes as default timeout. This paper uses standard benchmark datasets to analyze and compare our framework with two-tier prediction framework. Simulation results shows that our generated classifier framework WNPWR outperforms two-tier prediction framework in prediction accuracy and time.